One AI Assistant Configuration Guide

Introduction

The One AI Assistant Configuration Guide provides the steps to set up and manage access to One AI Assistant. Proper configuration is crucial for ensuring accurate, relevant outputs and maintaining secure control over who can use the tool. This guide covers permission settings, example prompt customization, and vector configurations, helping you tailor One AI Assistant for your team’s needs.

Permissioning One AI Assistant

In order to access One AI Assistant, connect with your Customer Success Lead to discuss your options for enabling this feature. 

Here is a link to the enablement instructions (for One Model employees only)

To see how the different roles and permissions interact and intersect, review our reference guide - Roles and Permissions.

Once One AI Assistant has been enabled by your CS team, there are a number of configuration options available.

Controlling Access to One AI Assistant

Access to One AI Assistant is controlled by the Application Access Role permission CanAccessOneAIAssistant. 

Controlling Access to Configure the One AI Assistant

The ability to make changes to the configuration of One AI Assistant is controlled by the Application Access Role permission CanConfigureOneAI. This permission is typically only enabled for site administrators. 

Configuring One AI Assistant

Users assigned to an Application Access Role with the permission CanConfigureOneAI enabled will see an option called One AI Configuration in the Admin menu on the navigation ribbon. Selecting this will load a screen with two sections.

1. Example Prompts Configuration

Example Prompts configuration via One AI Configuration

Example prompts in One AI Assistant 

The example prompts displayed on the initial One AI Assistant screen can be customized for your One Model instance. Changes made here will apply for all users. The ability to add custom images next to each prompt will be added in an upcoming release.

2. Vector Configuration

Vector Configuration via One AI Configuration

The metrics and dimensions that One AI Assistant has access to can be controlled for your One Model instance from the One AI Configuration screen, in addition to those controlled by data access roles for each user.  One AI Assistant respects role-based security in addition to its configuration. For example, if the Gender dimension is enabled in the Assistant’s configuration but a user’s data access role does not permit access to the Gender dimension, that user will not be able to build queries using it in One AI Assistant.

Admin & Configuration Best Practices

Since the assistant relies on a large language model (LLM) and a vector database to interpret prompts and match them with your data, thoughtful configuration is essential for accurate results.

1. Be deliberate in configuration: When configuring One AI Assistant, site administrators should carefully select which metrics and dimensions the assistant can access. Striking a balance is key—include enough data to support meaningful and interesting queries, but avoid overwhelming the assistant with similarly named metrics, dimensions, and dimension nodes. If a metric or dimension is rarely used or only relevant to a small group, it may not need to be included. Focus on metrics and dimensions that are widely relevant and useful, and avoid overloading the assistant with similar options like multiple "headcount" or "termination" metrics. This ensures the assistant can efficiently find and return the right data.
2. Exclude "Previous" dimensions: "Previous" dimensions (e.g., previous location, previous performance rating) are typically used for internal movement metrics, like transfers or promotions, and don’t apply to most other types of queries. If this applies to your One Model instance, consider excluding these dimensions from your One AI Assistant configuration since these dimensions contain the same nodes as their “Current” counterparts. This helps avoid confusion and irrelevant outputs, especially for casual users who may not fully understand the specific data requirements needed for these dimensions.
3. Avoid including multiple dimensions with similar nodes: Be mindful when configuring dimensions that have the same or very similar nodes (e.g., "work location" and "home location" both containing "Chicago"). If multiple dimensions share identical nodes, One AI Assistant may struggle to determine which one to use when you query data (e.g., "show me headcount over the last 12 months in Chicago"). To prevent confusion and inaccurate results, only include one relevant dimension, unless you are prepared to make minor edits in the query builder.
4. Exclude metrics and dimensions built for One AI predictive model storyboards: Avoid including metrics and dimensions that were built specifically for One AI predictive model storyboards. Since there’s currently no way to track the machine learning model's performance, when it was last run, or how these metrics interact with other data on the site, including them may result in inaccurate or misleading outputs. 
5. Exclude metrics that can be reached with dimension filters: If a metric can be reached using a dimension filter, don’t include it as a separate metric. This reduces the number of similarly named metrics and helps One AI Assistant return accurate results. For instance, instead of including a separate "Headcount - Female" metric, use the standard "Headcount (EOP)" metric and apply a gender filter for women. These metrics are typically included in order to calculate other metrics, such as “Headcount % - Female”. These calculated metrics are okay to include. 
6. Provide clear metric definitions for user clarity: Ensure that metric definitions are clear and easy to understand. These can be edited in the metric editor and are important because when users drillthrough a data point, the metric definition is also displayed. This helps more casual users verify that One AI Assistant is using the correct metric for their query, giving them confidence in the results. Additionally, admins can download all metric definitions from the ‘Metrics’ admin report to provide a "metric dictionary" for users who don’t have drill-through access, ensuring everyone has a reference to the metrics used.

Conclusion

This guide provides the steps for both setting up One AI Assistant and making adjustments for ongoing maintenance. With the right permissions, prompt customization, and configurations, your team can securely use the Assistant for reliable, relevant results, supporting a smooth and effective experience over time.